Algorithm configuration

Voice verification¶

Run multiple verification algorithms¶

IDVoice CC voice verification component is delivered with a set of configurations covering the most common use-cases and scenarios. Configuration can be set at the runtime using the configuration request's query parameter, e.g. /voice_template_factory/create_voice_template_from_file?configuration=tel-3.

Configurations to use can be configured using following environment variables:

IDRND_VOICESDK_VERIFY_DEFAULT_INIT_DATA (default configuration to use if the configuration query parameter is not supplied).
IDRND_VOICESDK_VERIFY_INIT_DATAS (available configurations to select from with the configuration parameter).

IDVoice speaker verification component configuration:

Shell

$ docker run -d --name vrss --publish 8080:8080 \
             -e IDRND_VOICESDK_VERIFY_INIT_DATAS="tel-3,other-configuration" \
             -e IDRND_VOICESDK_VERIFY_DEFAULT_INIT_DATA="tel-3" \
             voicesdk-cc-server:3.0

Available configurations:

tel-3 - init data for telephone channel text-independent/text-dependent speaker verification

The default configuration is text-independent speaker verification in telephone channel (tel-3).

Enable voice template compression ¶

It is possible to employ voice template compression to get smaller binary representations of voice template by setting the VOICESDK_USE_VOICE_TEMPLATE_COMPRESSION environment variable:

Shell

$ docker run -d --name vrss --publish 8080:8080 \
             -e VOICESDK_USE_VOICE_TEMPLATE_COMPRESSION=1 \
             voicesdk-cc-server:3.0

Enable voice template converter ¶

IDVoice CC Server provides REST API for voice templates conversion. By default, this part of REST API is disabled, in order to enable it set IDVOICE_CC_SERVER_TEMPLATE_CONVERTER environment variable to true:

Shell

$ docker run \
      --env IDVOICE_CC_SERVER_TEMPLATE_CONVERTER=true \
      ...

Voice template converter is delivered with a set of configurations. Configuration can be set at the runtime using the configuration request's query parameter, e.g. /voice_template_converter/convert_voice_template?configuration=tel-1_tel-3.

Configurations to use can be configured using following environment variables:

IDRND_VOICESDK_CORE_TEMPLATE_CONVERTER_DEFAULT_INIT_DATA (default configuration to use if the configuration query parameter is not supplied).
IDRND_VOICESDK_CORE_TEMPLATE_CONVERTER_INIT_DATAS (available configurations to select from with the configuration parameter).

Available configurations:

tel-1_tel-3 - Configuration that enables conversion from tel-1 voice template to tel-3 voice template.

The default configuration is tel-1_tel-3.

IDVoice CC Server voice template conversion configuration:

Shell

$ docker run -d --name vrss --publish 8080:8080 \
             -e IDRND_VOICESDK_CORE_TEMPLATE_CONVERTER_INIT_DATAS="tel-1_tel-3,other-configuration" \
             -e IDRND_VOICESDK_CORE_TEMPLATE_CONVERTER_DEFAULT_INIT_DATA="tel-1_tel-3" \
             voicesdk-cc-server:3.0